© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 10100
    Prev
    Next
    INDEX
    Explanations

    words related to communication and conversation

    oai_token-act-pair · gemini-2.0-flash

    language speakers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    aarrggbb
    -0.85
    AsUp
    -0.81
     kasarigan
    -0.80
    #+#
    -0.79
     propOrder
    -0.77
    SizeMode
    -0.75
    Chham
    -0.73
    GEBURTSDATUM
    -0.68
    Geplaatst
    -0.63
    หวัด
    -0.62
    POSITIVE LOGITS
     SPEAKER
    0.59
     Speaker
    0.57
     speaker
    0.57
     Neurol
    0.54
     speakers
    0.54
    Speaker
    0.52
     bilingual
    0.52
     Bilingual
    0.52
     language
    0.51
     linguistic
    0.51
    Activations Density 1.257%

    No Known Activations